Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    by a legal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anticipate
    0.49
    ㉖
    0.46
    鴻
    0.46
    ೇಷ
    0.45
     custom
    0.44
     prejudiced
    0.44
    InterfaceLine
    0.44
    ガン
    0.43
     क्वेश्च
    0.43
     customized
    0.43
    POSITIVE LOGITS
    ose
    0.46
    ก่อน
    0.44
     I
    0.42
     Marina
    0.42
     Anna
    0.41
    เรีย
    0.41
    akkam
    0.41
     Mrs
    0.40
     Assam
    0.40
    ipat
    0.40
    Act Density 0.001%

    No Known Activations